This paper introduces a formulation which allows using wavelet-based priors for image segmentation. This formulation can be used in supervised, unsupervised, or semisupervised mod...
We present a multiscale method for motion segmentation. Our method begins with local, ambiguous optical flow measurements. It uses a process of aggregation to resolve the ambiguit...
Projection systems can be used to implement augmented reality, as well as to create both displays and interfaces on ordinary surfaces. Ordinary surfaces have varying reflectance, ...
Kensaku Fujii, Michael D. Grossberg, Shree K. Naya...
Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the h...
Those motion parameters that cannot be recovered from image measurements are unobservable in the visual dynamic system. This paper studies this important issue of singularity in th...
Interactive or semi-automatic segmentation is a useful alternative to pure automatic segmentation in many applications. While automatic segmentation can be very challenging, a sma...
We present a quantitative evaluation of SE-MinCut, a novel segmentation algorithm based on spectral embedding and minimum cut. We use human segmentations from the Berkeley Segment...
Illumination changes are a ubiquitous problem in computer vision. They present a challenge in many applications, including tracking: for example, an object may move in and out of ...
We describe a novel technique for identifying semantically equivalent parts in images belonging to the same object class, (e.g. eyes, license plates, aircraft wings etc.). The vis...
The recent explosion of interest in graph cut methods in computer vision naturally spawns the question: what energy functions can be minimized via graph cuts? This question was fi...